基于先验知识引导的U-Net用于乳腺癌改良根治术后放疗临床靶区自动分割
该研究回顾性收集102例乳腺癌改良根治术后患者的CT扫描,训练集80例采用5折交叉验证,独立测试集22例,设计两阶段先验知识引导U-Net(PK-UNet)自动分割胸壁、锁骨上区和腋窝III组临床靶区。PK-UNet平均DSC为0.90±0.02,95%豪斯多夫距离2.82±1.29 mm,81.8%的预测轮廓被2名放疗科医生随机双盲四级客观量表评价为可接受临床应用,平均手动修正时间降至1.02分钟,较手动勾画18.20分钟减少94.4%。
要点
- PK-UNet自动分割乳腺癌改良根治术后CTV,平均DSC为0.90±0.02,95%豪斯多夫距离2.82±1.29 mm。
- 81.8%的预测轮廓经2名放疗科医生随机双盲四级客观量表评价为可接受临床应用。
- 平均手动修正时间1.02分钟,较手动勾画18.20分钟减少94.4%。
核心结论
- 本研究首次将先验医学知识整合到深度学习框架中用于乳腺癌改良根治术后放疗,应对CTV分割挑战并提高临床工作流程效率。
研究设计与样本
- 回顾性收集102例乳腺癌改良根治术后患者的CT扫描,其中80例用于5折交叉验证训练,22例用于独立测试。
- CTV包括胸壁、锁骨上区和腋窝III组。
- PK-UNet采用两阶段自动分割流程:定位网络基于CTV解剖信息对CT切片分类并生成先验知识标签,输出与CT图像一起输入最终分割网络。
- 定量评价采用平均Dice相似系数(DSC)、95%豪斯多夫距离、平均表面距离和表面DSC。
- 由2名经验丰富的放疗科医生以随机双盲方式进行四级客观量表评价。
主要发现
- PK-UNet定量评价显著优于当前最先进的分割方法(P < .01),平均DSC为0.90±0.02,95%豪斯多夫距离为2.82±1.29 mm。
- PK-UNet平均表面距离为0.91±0.22 mm,表面DSC为0.84±0.07,显著优于AdwU-Net(P < .01),与其他模型结果相当。
- 临床评价证实PK-UNet的有效性,81.8%的预测轮廓可接受用于临床应用。
- PK-UNet自动分割优势在上层和下层切片以及不同亚区交界处不连续切片中最明显。
- 平均手动修正时间降至1.02分钟,相比手动勾画的18.20分钟减少94.4%工作时间。
关键数值与推荐
- 平均DSC为0.90±0.02,95%豪斯多夫距离为2.82±1.29 mm。
- 平均表面距离为0.91±0.22 mm,表面DSC为0.84±0.07。
- 81.8%的预测轮廓经2名放疗科医生随机双盲四级客观量表评价为可接受临床应用。
- 平均手动修正时间为1.02分钟,手动勾画时间为18.20分钟,工作时间减少94.4%。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: This study aimed to design and evaluate a prior-knowledge-guided U-Net (PK-UNet) for automatic clinical target volume (CTV) segmentation in postmastectomy radiation therapy for breast cancer. METHODS AND MATERIALS: A total of 102 computed tomography (CT) scans from breast cancer patients who underwent postmastectomy were retrospectively collected. Of these, 80 scans were used for training with 5-fold cross-validation, and 22 scans for independent testing. The CTV included the chest wall, supraclavicular region, and axillary group III. The proposed PK-UNet method employs a 2-stage auto-segmentation process. Initially, the localization network categorizes CT slices based on the anatomic information of the CTV and generates prior knowledge labels. These outputs, along with the CT images, were fed into the final segmentation network. Quantitative evaluation was conducted using the mean Dice similarity coefficient (DSC), 95% Hausdorff distance, average surface distance, and surface DSC. A four-level objective scale evaluation was performed by 2 experienced radiation oncologists in a randomized double-blind manner. RESULTS: Quantitative evaluations revealed that PK-UNet significantly outperformed state-of-the-art segmentation methods (P < .01), with a mean DSC of 0.90 ± 0.02 and a 95% Hausdorff distance of 2.82 ± 1.29 mm. The mean average surface distance of PK-UNet was 0.91 ± 0.22 mm and the surface DSC was 0.84 ± 0.07, significantly surpassing the performance of AdwU-Net (P < .01) and showing comparable results to other models. Clinical evaluation confirmed the efficacy of PK-UNet, with 81.8% of the predicted contours being acceptable for clinical application. The advantages of the auto-segmentation capability of PK-UNet were most evident in the superior and inferior slices and slices with discontinuities at the junctions of different subregions. The average manual correction time was reduced to 1.02 min, compared with 18.20 min for manual contouring leading to a 94.4% reduction in working time. CONCLUSIONS: This study introduced the pioneering integration of prior medical knowledge into a deep learning framework for postmastectomy radiation therapy. This strategy addresses the challenges of CTV segmentation in postmastectomy radiation therapy and improves clinical workflow efficiency.
引用
- Deng XW, Zhao HM, Jia LC, et al. Prior Knowledge-Guided U-Net for Automatic Clinical Target Volume Segmentation in Postmastectomy Radiation Therapy of Breast Cancer. Int J Radiat Oncol Biol Phys. 2024. PMID: 39667584. doi:10.1016/j.ijrobp.2024.11.104
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。